incorrect repo name in the sample for llama.cpp: "Repository is not GGUF or is not compatible with llama.cpp"
#1
by
j-m
- opened
There is a typo in the quickstart for llama.cpp
./llama-cli -hf Qwen/Qwen3-32B:Q8_0 --jinja --color -ngl 99 -fa -sm row --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0 --presence-penalty 1.5 -c 40960 -n 32768 --no-context-shift
results in "Repository is not GGUF or is not compatible with llama.cpp"
I gather this should be:
./llama-cli -hf Qwen/Qwen3-32B-GGUF:Q8_0 --jinja --color -ngl 99 -fa -sm row --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0 --presence-penalty 1.5 -c 40960 -n 32768 --no-context-shift